Skip to main content
ConductScienceScienceDex
zenodoopen

modelforge curated dataset: ANI-2x

<h1><strong>Modelforge Curated ANI-2x Dataset:</strong><br><strong>- 1000 configuration test set</strong><strong><br></strong><strong>-&nbsp;</strong><strong>Version: nc_1000_v1.1</strong></h1> <p>This provides a curated hdf5 file for a subset of the ANI-2x dataset designed to be compatible with <a href="https://github.com/choderalab/modelforge">modelforge</a>, an infrastructure to implement and train NNPs. &nbsp;This dataset contains 101 unique records for 1000&nbsp; total configurations, with a maximum of 10 per system. &nbsp; Note, configurations are parititioned into records based on the array of atomic species appearing in sequence in the source data file.</p> <p>When applicable, the units of properties are provided in the datafile,&nbsp; encoded as strings compatible with the <a href="https://github.com/openforcefield/openff-units/">openff-units</a> package.&nbsp; For more information about the structure of the data file, please see the following:</p> <p>This dataset is compatible with modelforge hdf5 schema 2.</p> <h3><strong>Properties Included:&nbsp; &nbsp;&nbsp;&nbsp;</strong></h3> <ul> <li>atomic_numbers&nbsp;</li> <li>positions &nbsp; &nbsp; &nbsp;&nbsp; <ul> <li>"per_atom"</li> <li>&nbsp;"nanometer"</li> </ul> </li> <li>forces&nbsp;&nbsp; <ul> <li>"per_atom"</li> <li>&nbsp;"kilojoule_per_mole / nanometer"</li> </ul> </li> <li>energies &nbsp; &nbsp; &nbsp;&nbsp;&nbsp; <ul> <li>"per_system"</li> <li>"kilojoule_per_mole"</li> </ul> </li> </ul> <h3><strong>Source Dataset:</strong></h3> <div> <p>The ANI-2x data set includes properties for small organic molecules that contain&nbsp;H, C, N, O, S, F, and Cl. This dataset contains 9651712 conformers. This data was generated with the wB97X/631Gd level of theory&nbsp;used in the original ANI-2x paper, calculated using Gaussian 09.</p> </div> <h3>Citations:</h3> <p><em>ANI-2x publication:</em></p> <ul> <li> <div> <p>Devereux, C, Zubatyuk, R., Smith, J. et al.&nbsp;"Extending the applicability of the ANI deep learning molecular potential to sulfur and halogens."&nbsp;Journal of Chemical Theory and Computation 16.7 (2020): 4192-4202.&nbsp;<a href="https://doi.org/10.1021/acs.jctc.0c00121">https://doi.org/10.1021/acs.jctc.0c00121</a></p> </div> </li> </ul> <p><em>Source dataset, released with CC Attribution 4.0 International license:</em></p> <ul> <li>Huddleston, K., Zubatyuk, R., Smith, J., Roitberg, A., Isayev, O., Pickering, I., Devereux, C., &amp; Barros, K. (2023). ANI-2x Release [Data set]. Zenodo. <a href="https://doi.org/10.5281/zenodo.10108942" target="_blank" rel="noopener">https://doi.org/10.5281/zenodo.10108942</a></li> </ul>

ShareScore

40/100

Overall dataset sharing score

Score breakdown

These five areas show where the dataset supports — or may limit — practical reuse.

Stewardship
4
Harmonization
4
Access
20
Reuse readiness
8
Engagement
4

Dataset details

Repository
zenodo
Published
June 12, 2024
License
cc-by-4.0
DOI
10.5281/zenodo.11642743

Scored with release 0.9.0

ScienceDex for faculty

Your academic CV and NIH biosketch

Make your CV in your school's format and your NIH biosketch from it, then download both as Word files.